Fluid segmentation in Neutrosophic domain

TL;DR

This paper introduces a fast clustering method in the neutrosophic domain for fluid segmentation in OCT images, improving accuracy in detecting AMD and DME related fluid regions.

Contribution

It adapts the neutrosophic C-means clustering with a new cost function and gradient descent optimization for efficient fluid segmentation in OCT images.

Findings

Outperforms existing methods by 6% in dice coefficient

Achieves higher sensitivity in fluid detection

Provides a fast and effective segmentation approach

Abstract

Optical coherence tomography (OCT) as retina imaging technology is currently used by ophthalmologist as a non-invasive and non-contact method for diagnosis of agerelated degeneration (AMD) and diabetic macular edema (DME) diseases. Fluid regions in OCT images reveal the main signs of AMD and DME. In this paper, an efficient and fast clustering in neutrosophic (NS) domain referred as neutrosophic C-means is adapted for fluid segmentation. For this task, a NCM cost function in NS domain is adapted for fluid segmentation and then optimized by gradient descend methods which leads to binary segmentation of OCT Bscans to fluid and tissue regions. The proposed method is evaluated in OCT datasets of subjects with DME abnormalities. Results showed that the proposed method outperforms existing fluid segmentation methods by 6% in dice coefficient and sensitivity criteria.